Related papers: A High-Throughput Compute-Efficient POMDP Hide-And…

Multi-agent active perception is a task where a team of agents cooperatively gathers observations to compute a joint estimate of a hidden variable. The task is decentralized and the joint estimate can only be computed after the task ends by…

Efficient Reduce and AllReduce communication collectives are a critical cornerstone of high-performance computing (HPC) applications. We present the first systematic investigation of Reduce and AllReduce on the Cerebras Wafer-Scale Engine…

Multimodal Large Language Models (MLLMs) have empowered embodied agents with remarkable capabilities in planning and reasoning. However, when facing ambiguous natural language instructions (e.g., "fetch the tool" in a cluttered room),…

Deep reinforcement learning (DRL) is capable of learning high-performing policies on a variety of complex high-dimensional tasks, ranging from video games to robotic manipulation. However, standard DRL methods often suffer from poor sample…

Agentic AI require persistent memory to store user-specific histories beyond the limited context window of LLMs. Existing memory systems use dense vector databases or knowledge-graph traversal (or hybrid), incurring high retrieval latency…

Genomic sequence alignment is an important research topic in bioinformatics and continues to attract significant efforts. As genomic data grow exponentially, however, most of alignment methods face challenges due to their huge computational…

This paper proposes an intent-aware multi-agent planning framework as well as a learning algorithm. Under this framework, an agent plans in the goal space to maximize the expected utility. The planning process takes the belief of other…

Deep reinforcement learning agents progressively lose representational capacity during training: neurons become dormant, removing active capacity from the network, and effective rank collapses, leaving surviving neurons redundant. Existing…

Secure Multi-party Computation (MPC) enables untrusted parties to jointly compute a function without revealing their inputs. Its application to machine learning (ML) has gained significant attention, particularly for secure inference…

As fusion energy devices advance, plasma simulations are crucial for reactor design. Our work extends BIT1 hybrid parallelization by integrating MPI with OpenMP and OpenACC, focusing on asynchronous multi-GPU programming. Results show…

This paper presents a benchmarking study of some of the state-of-the-art reinforcement learning algorithms used for solving two simulated vision-based robotics problems. The algorithms considered in this study include soft actor-critic…

IEEE 802.11be -Extremely High Throughput-, commercially known as Wireless-Fidelity (Wi-Fi) 7 is the newest IEEE 802.11 amendment that comes to address the increasingly throughput hungry services such as Ultra High Definition (4K/8K) Video…

Multi-party computation (MPC) is a branch of cryptography where multiple non-colluding parties execute a well designed protocol to securely compute a function. With the non-colluding party assumption, MPC has a cryptographic guarantee that…

We study sample efficient reinforcement learning (RL) under the general framework of interactive decision making, which includes Markov decision process (MDP), partially observable Markov decision process (POMDP), and predictive state…

Data race, a category of insidious software concurrency bugs, is often challenging and resource-intensive to detect and debug. Existing dynamic race detection tools incur significant execution time and memory overhead while exhibiting high…

This article presents an optimized algorithm and implementation for calculating resolution-of-the-identity Hartree-Fock (RI-HF) energies and analytic gradients using multiple Graphics Processing Units (GPUs). The algorithm is especially…

Heterogeneous embedded systems on chip (HESoCs) co-integrate a standard host processor with programmable manycore accelerators (PMCAs) to combine general-purpose computing with domain-specific, efficient processing capabilities. While…

This paper summarizes the ideas and key concepts in MISE (Memory Interference-induced Slowdown Estimation), which was published in HPCA 2013 [97], and examines the work's significance and future potential. Applications running concurrently…

Recent works have introduced LEAPS and HPRL, systems that learn latent spaces of domain-specific languages, which are used to define programmatic policies for partially observable Markov decision processes (POMDPs). These systems induce a…

We present a novel method for Deep Reinforcement Learning (DRL), incorporating the convex property of the value function over the belief space in Partially Observable Markov Decision Processes (POMDPs). We introduce hard- and soft-enforced…